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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 133
    Prev
    Next
    INDEX
    Explanations

    pipe symbol

    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
    PLE
    -0.09
    gne
    -0.09
    ジェ
    -0.08
    τός
    -0.08
    оуп
    -0.08
    WISE
    -0.07
    phinx
    -0.07
    COPE
    -0.07
    ynamo
    -0.07
    Вот
    -0.07
    POSITIVE LOGITS
     Again
    0.09
     vielä
    0.08
     Choosing
    0.08
     encore
    0.08
     delve
    0.08
    ​ប្រ�
    0.08
     Datenschutz
    0.08
     again
    0.08
     опять
    0.08
     nochmals
    0.07
    Activations Density 0.040%

    No Known Activations