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. 58836
    Prev
    Next
    INDEX
    Explanations

    tense

    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
     pill
    -0.09
     Cancellation
    -0.08
    887
    -0.07
    emens
    -0.07
     Boer
    -0.07
    )throws
    -0.07
    _ACTION
    -0.07
     ‘‘
    -0.07
    िकी
    -0.07
     ходе
    -0.07
    POSITIVE LOGITS
    /F
    0.08
    fed
    0.08
    eva
    0.08
     appeals
    0.08
    wem
    0.08
    യിൽ
    0.07
     rq
    0.07
     تناول
    0.07
    -ed
    0.07
     ond
    0.07
    Activations Density 0.001%

    No Known Activations