© 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. 45466
    Prev
    Next
    INDEX
    Explanations

    semicolon

    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
     normative
    -0.09
     vantage
    -0.08
     groundwater
    -0.08
     Clouds
    -0.08
    あり
    -0.08
     осн
    -0.08
    igay
    -0.08
     And
    -0.08
     yük
    -0.08
     اين
    -0.08
    POSITIVE LOGITS
    .android
    0.09
    assembler
    0.08
    �
    0.08
    �
    0.08
    .error
    0.07
    Secure
    0.07
     Secure
    0.07
    Strateg
    0.07
    183
    0.07
    ดาว
    0.07
    Activations Density 0.000%

    No Known Activations