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. 130020
    Prev
    Next
    INDEX
    Explanations

    integers

    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
    .Jwt
    -0.08
     Pará
    -0.08
     twists
    -0.08
    Parity
    -0.08
    .jpeg
    -0.08
    Attr
    -0.07
     prens
    -0.07
     decorated
    -0.07
     Principle
    -0.07
    Parallel
    -0.07
    POSITIVE LOGITS
    落
    0.09
     lurking
    0.09
     fencing
    0.08
     Merr
    0.08
    多数
    0.08
    -spacing
    0.08
    _AVAILABLE
    0.08
    来说
    0.08
     borderline
    0.08
    ذك
    0.08
    Activations Density 0.025%

    No Known Activations