© 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. 64954
    Prev
    Next
    INDEX
    Explanations

    creative writing instructions

    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
    jó
    -0.08
    /json
    -0.08
     typings
    -0.08
    Joining
    -0.07
    ãs
    -0.07
    <?=$
    -0.07
    Wnd
    -0.07
    -0.07
    adre
    -0.07
    Christian
    -0.07
    POSITIVE LOGITS
     مراحل
    0.11
    阶段
    0.11
     stages
    0.10
     этап
    0.10
     مرحله
    0.10
     progressively
    0.10
     vaihe
    0.10
     phases
    0.10
     단계
    0.10
     tahap
    0.09
    Activations Density 0.069%
    No Known Activations