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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 56004
    Prev
    Next
    INDEX
    Explanations

    stripes

    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
     anthrop
    -0.09
     engagements
    -0.08
    [...]
    -0.08
     heur
    -0.08
    (+
    -0.08
     heuristic
    -0.07
    _SU
    -0.07
     Anthrop
    -0.07
     conting
    -0.07
    escu
    -0.07
    POSITIVE LOGITS
    纹
    0.14
     stripes
    0.14
    -striped
    0.13
     alternating
    0.12
     striped
    0.12
    Pattern
    0.11
    _PATTERN
    0.11
     patterns
    0.11
    (pattern
    0.10
     Pattern
    0.10
    Activations Density 0.032%

    No Known Activations