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. 109287
    Prev
    Next
    INDEX
    Explanations

    directions

    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
    -0.07
     estrem
    -0.07
     ban
    -0.07
    authorized
    -0.07
     والن
    -0.07
    xtype
    -0.07
    .sig
    -0.07
     tranh
    -0.07
     Highest
    -0.07
    ив
    -0.07
    POSITIVE LOGITS
     нескольких
    0.08
    Suit
    0.08
    ရွ
    0.08
    LOD
    0.08
    ოგ
    0.07
    Ấ
    0.07
    აში
    0.07
     respecto
    0.07
    男
    0.07
    HUD
    0.07
    Activations Density 0.008%

    No Known Activations