© 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. 110295
    Prev
    Next
    INDEX
    Explanations

    Text generation

    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
     Tiger
    -0.08
     ori
    -0.08
     Holly
    -0.08
    olly
    -0.07
    LError
    -0.07
    �
    -0.07
     Cashback
    -0.07
    exact
    -0.07
    ALLY
    -0.07
    ”↵↵
    -0.07
    POSITIVE LOGITS
     revised
    0.08
    涵
    0.08
     reputable
    0.07
     factual
    0.07
     overview
    0.07
     Supporting
    0.07
     enzyme
    0.07
     enum
    0.07
     supporting
    0.07
     redesigned
    0.07
    Activations Density 0.170%

    No Known Activations