© 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. 7-RESID-POST-AA
    11. 1372
    Prev
    Next
    INDEX
    Explanations

    isa

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ások
    -0.07
     antioxid
    -0.07
     Kan
    -0.07
     lung
    -0.07
     oils
    -0.07
    agad
    -0.07
    െടുക്ക
    -0.07
    Kan
    -0.07
     hav
    -0.07
    italic
    -0.07
    POSITIVE LOGITS
     يمن
    0.08
    YX
    0.08
     والن
    0.07
     stitched
    0.07
     Numer
    0.07
    .timeline
    0.07
     업데이트
    0.07
     menstru
    0.07
     inexp
    0.07
    Advice
    0.07
    Activations Density 0.001%

    No Known Activations