© 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. 95163
    Prev
    Next
    INDEX
    Explanations

    River

    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
     elect
    -0.09
     equiv
    -0.07
    TL
    -0.07
     eri
    -0.07
    来自
    -0.07
    Hol
    -0.07
     usc
    -0.07
    impi
    -0.07
    TS
    -0.07
    toe
    -0.07
    POSITIVE LOGITS
    چه
    0.09
    boats
    0.08
     supr
    0.08
     barg
    0.08
     Metall
    0.08
     dài
    0.08
    buf
    0.07
    banks
    0.07
    bank
    0.07
     People
    0.07
    Activations Density 0.016%

    No Known Activations