© 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. 47446
    Prev
    Next
    INDEX
    Explanations

    question

    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
     hectare
    -0.08
     odp
    -0.07
     nich
    -0.07
     borrowed
    -0.07
    очных
    -0.07
     Valent
    -0.07
    akken
    -0.07
     degr
    -0.07
    ечных
    -0.07
    我要
    -0.07
    POSITIVE LOGITS
     plaus
    0.09
     inconsistent
    0.08
    _ATTRIBUTES
    0.08
     sandals
    0.07
    Œ
    0.07
     puzzled
    0.07
     consistency
    0.07
     Reciprocity
    0.07
    енье
    0.07
     incons
    0.07
    Activations Density 0.002%

    No Known Activations