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. 9163
    Prev
    Next
    INDEX
    Explanations

    question marks

    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
     ducts
    -0.08
    elo
    -0.08
     breeder
    -0.07
     welchen
    -0.07
     breeding
    -0.07
     view
    -0.07
     graphic
    -0.07
     sh
    -0.07
    ush
    -0.07
     loại
    -0.07
    POSITIVE LOGITS
    pare
    0.09
    ERRUP
    0.08
    빛
    0.08
    VERTISE
    0.08
    يار
    0.08
    ّ
    0.08
    -U
    0.08
    ഗ്
    0.08
    Communication
    0.08
    பல
    0.08
    Activations Density 0.007%

    No Known Activations