© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 110962
    Prev
    Next
    INDEX
    Explanations

    to

    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
     acclaim
    -0.08
     ANC
    -0.08
     aware
    -0.08
    antly
    -0.07
    মূল
    -0.07
     tahu
    -0.07
    Jul
    -0.07
    yr
    -0.07
     उतर
    -0.07
    イトル
    -0.07
    POSITIVE LOGITS
     eid
    0.08
     Gross
    0.08
     Bolton
    0.08
    gart
    0.08
     Achilles
    0.08
    onces
    0.07
     eo
    0.07
    hing
    0.07
     Kap
    0.07
     verlaten
    0.07
    Activations Density 0.011%

    No Known Activations