© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 1148
    Prev
    Next
    INDEX
    Explanations

    half

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    outh
    -0.08
    requency
    -0.07
    AV
    -0.07
    ht
    -0.07
    itag
    -0.07
     слов
    -0.07
    (iter
    -0.07
     Acr
    -0.07
    iterate
    -0.07
    thel
    -0.07
    POSITIVE LOGITS
     "***
    0.09
     Validators
    0.08
     sensations
    0.08
     [].
    0.08
     arquivo
    0.07
    ामी
    0.07
    šte
    0.07
     afzonder
    0.07
     ----------------------------------------------------------------------------------------------------------------
    0.07
    anlagen
    0.07
    Activations Density 0.001%

    No Known Activations