Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 78758
    Prev
    Next
    INDEX
    Explanations

    parametric equations

    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
     devol
    -0.08
     emot
    -0.08
     overweight
    -0.07
     unders
    -0.07
     konte
    -0.07
    -0.07
    قد
    -0.07
     chest
    -0.07
     anatomy
    -0.07
     scrutin
    -0.07
    POSITIVE LOGITS
    号
    0.09
     मु
    0.08
    .Time
    0.08
    .states
    0.08
    hofer
    0.08
    ieg
    0.08
    (tx
    0.08
     Wishes
    0.08
    ziemy
    0.08
     whim
    0.08
    Activations Density 0.026%

    No Known Activations