© 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. 65508
    Prev
    Next
    INDEX
    Explanations

    Review

    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
     biomass
    -0.09
     Logistic
    -0.08
     Ernährung
    -0.08
     Biom
    -0.08
     medicinal
    -0.08
     starving
    -0.08
     ev
    -0.08
     machinery
    -0.08
    IRS
    -0.08
     tissues
    -0.08
    POSITIVE LOGITS
     physics
    0.10
     astroph
    0.10
     firebase
    0.09
    .physics
    0.09
     rendu
    0.09
    physics
    0.08
    firebase
    0.08
     Jupiter
    0.08
    olar
    0.08
     Physics
    0.08
    Activations Density 0.004%

    No Known Activations