© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 54688
    Prev
    Next
    INDEX
    Explanations

    Ramsey

    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
     jeden
    -0.08
     refl
    -0.07
     capa
    -0.07
     censor
    -0.07
     caps
    -0.07
     gov
    -0.07
    othe
    -0.07
     buffering
    -0.07
     Caps
    -0.07
     afro
    -0.07
    POSITIVE LOGITS
    -hover
    0.08
     noted
    0.08
    ustada
    0.08
    াড়
    0.08
    ួ
    0.08
     hir
    0.08
     liberated
    0.07
    KHTML
    0.07
    출장안마
    0.07
    .Inject
    0.07
    Activations Density 0.000%

    No Known Activations