© 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. 23-RESID-POST-AA
    11. 6436
    Prev
    Next
    INDEX
    Explanations

    /A

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kijk
    -0.08
     ANC
    -0.08
     alc
    -0.08
     તમ
    -0.08
     kig
    -0.08
     yank
    -0.07
     Solution
    -0.07
     Answers
    -0.07
     Rough
    -0.07
     Jim
    -0.07
    POSITIVE LOGITS
    IME
    0.14
    OPS
    0.12
    ops
    0.12
    haps
    0.09
    _ops
    0.09
    o
    0.08
    pertoire
    0.08
    +#
    0.08
    something
    0.08
    ime
    0.08
    Activations Density 0.001%

    No Known Activations