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. 58337
    Prev
    Next
    INDEX
    Explanations

    House

    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
     Bade
    -0.09
    идан
    -0.08
     Haus
    -0.08
     Mitt
    -0.08
     bequem
    -0.08
    ounded
    -0.08
     envelop
    -0.08
     Viet
    -0.07
    entation
    -0.07
     Nort
    -0.07
    POSITIVE LOGITS
     aprov
    0.08
     drastically
    0.08
     extraordinarily
    0.08
     exagger
    0.08
     motto
    0.08
    __((
    0.08
    ♥
    0.08
     mantra
    0.08
    аяв
    0.08
     gcd
    0.08
    Activations Density 0.001%

    No Known Activations