© 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. 75558
    Prev
    Next
    INDEX
    Explanations

    website grid layouts

    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
    zig
    -0.08
     unilateral
    -0.08
     notwend
    -0.08
    anal
    -0.07
     hanze
    -0.07
     zig
    -0.07
    gment
    -0.07
    unic
    -0.07
    anges
    -0.07
     Comunic
    -0.07
    POSITIVE LOGITS
    _SZ
    0.08
    0.08
    铺
    0.08
     տ
    0.07
     Saves
    0.07
     Aquarium
    0.07
     trop
    0.07
     берген
    0.07
     exhibitions
    0.07
     tendance
    0.07
    Activations Density 0.002%
    No Known Activations