© 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. 65400
    Prev
    Next
    INDEX
    Explanations

    brainstorming

    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
     Ast
    -0.07
     harte
    -0.07
    स्ता
    -0.07
    ுவர்
    -0.07
    geld
    -0.07
    asta
    -0.07
    ஆ
    -0.07
     ஆ
    -0.07
    厚
    -0.07
    idi
    -0.07
    POSITIVE LOGITS
     brainstorm
    0.10
     brainstorming
    0.10
     kring
    0.10
     ideas
    0.09
     আলোচনা
    0.08
     بشأن
    0.08
     constructive
    0.08
     aloud
    0.08
     consens
    0.08
     Ideen
    0.08
    Activations Density 0.005%

    No Known Activations