© 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. 75683
    Prev
    Next
    INDEX
    Explanations

    win

    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
    and
    -0.08
     Mein
    -0.07
    aví
    -0.07
     Mont
    -0.07
    Wallet
    -0.07
     Weil
    -0.07
     Ged
    -0.07
    RAL
    -0.07
    .cid
    -0.07
    Fetch
    -0.06
    POSITIVE LOGITS
     abroad
    0.09
     procession
    0.09
     chassis
    0.08
     tendencies
    0.08
     outright
    0.08
    cios
    0.08
     grados
    0.08
     преиму
    0.08
     നേടിയ
    0.07
    osm
    0.07
    Activations Density 0.019%

    No Known Activations