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. 119448
    Prev
    Next
    INDEX
    Explanations

    reached

    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
     timestep
    -0.08
     Bols
    -0.08
     procession
    -0.07
     strip
    -0.07
     beweg
    -0.07
    brecht
    -0.07
     movable
    -0.07
     مجموعة
    -0.07
    achter
    -0.07
     Kirch
    -0.07
    POSITIVE LOGITS
    .favorite
    0.09
    etsy
    0.09
    -esteem
    0.09
    .email
    0.08
    Lauren
    0.08
    eches
    0.08
    uindo
    0.08
    .salary
    0.08
     prefe
    0.08
     gewoon
    0.08
    Activations Density 0.006%

    No Known Activations