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. 29972
    Prev
    Next
    INDEX
    Explanations

    .

    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
     konuda
    -0.08
     movie
    -0.08
     oka
    -0.07
    PR
    -0.07
    ացում
    -0.07
    даны
    -0.07
    ixing
    -0.07
     cosmic
    -0.07
    bbc
    -0.07
     Definit
    -0.07
    POSITIVE LOGITS
     Lindsay
    0.09
     �
    0.08
     Farrell
    0.08
    inese
    0.08
     Nad
    0.07
     pharmacist
    0.07
     Bowen
    0.07
     yours
    0.07
    ичным
    0.07
    _ass
    0.07
    Activations Density 0.000%

    No Known Activations