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. 113965
    Prev
    Next
    INDEX
    Explanations

    start or middle of text

    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
    Prere
    -0.08
     prec
    -0.08
    .codegen
    -0.08
     Lesser
    -0.08
    不用
    -0.08
     Synopsis
    -0.08
     außergewöhn
    -0.08
     nona
    -0.08
     aparat
    -0.08
    頂
    -0.08
    POSITIVE LOGITS
    й
    0.08
     E
    0.08
    uvre
    0.07
     Ke
    0.07
     K
    0.07
    keer
    0.07
    ql
    0.07
    \",
    0.07
    kk
    0.07
     instance
    0.07
    Activations Density 0.681%

    No Known Activations