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. 102956
    Prev
    Next
    INDEX
    Explanations

    ё

    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
     Wey
    -0.08
     mortal
    -0.08
    Prescription
    -0.08
     Felt
    -0.07
    Composer
    -0.07
     downturn
    -0.07
    યો
    -0.07
     homeowner
    -0.07
     tabletop
    -0.07
     Omaha
    -0.07
    POSITIVE LOGITS
     Kal
    0.07
     puk
    0.07
     Gull
    0.07
     Proper
    0.07
     selecting
    0.07
    140
    0.07
    aqu
    0.07
    Umb
    0.07
    unya
    0.07
    繁
    0.07
    Activations Density 0.003%

    No Known Activations