Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 49388
    Prev
    Next
    INDEX
    Explanations

    pi

    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
     Bou
    -0.08
     atrav
    -0.08
     cul
    -0.08
    兑现
    -0.08
     બચ
    -0.07
     వెంట
    -0.07
    uter
    -0.07
     waɗ
    -0.07
     poor
    -0.07
     конс
    -0.07
    POSITIVE LOGITS
    _shift
    0.08
     rotated
    0.08
     bevo
    0.08
    -equiv
    0.08
     added
    0.08
    posé
    0.08
    shift
    0.08
     rotates
    0.08
    ienst
    0.07
     seems
    0.07
    Activations Density 0.011%

    No Known Activations