© 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. 8176
    Prev
    Next
    INDEX
    Explanations

    ala

    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
     hurdles
    -0.08
     princip
    -0.08
     hurdle
    -0.08
     UW
    -0.08
     отраж
    -0.07
     Bumble
    -0.07
    �
    -0.07
    igno
    -0.07
    вает
    -0.07
     IW
    -0.07
    POSITIVE LOGITS
     substances
    0.10
    汁
    0.10
     �
    0.10
    �
    0.09
     strawberry
    0.09
     पदार्थ
    0.09
     substance
    0.08
     visc
    0.08
     toxic
    0.08
    �
    0.08
    Activations Density 0.215%

    No Known Activations