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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 112235
    Prev
    Next
    INDEX
    Explanations

    C struct definitions

    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
    gada
    -0.09
    .tree
    -0.07
    ায়ের
    -0.07
     Bünd
    -0.07
     Visit
    -0.07
     dum
    -0.07
     Elite
    -0.07
    (find
    -0.07
     dias
    -0.07
     dance
    -0.07
    POSITIVE LOGITS
    除了
    0.08
     reass
    0.08
     Apart
    0.08
    째
    0.08
     longitudinal
    0.07
     пом
    0.07
     abdominal
    0.07
    uminen
    0.07
    ్ప
    0.07
     besides
    0.07
    Activations Density 0.000%

    No Known Activations