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. 106031
    Prev
    Next
    INDEX
    Explanations

    wisdom teeth

    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
    SIGN
    -0.08
    _SIGN
    -0.08
    _SIGNATURE
    -0.08
    ARIA
    -0.08
    &T
    -0.08
     Griffin
    -0.07
    _COUNTER
    -0.07
    LOGIN
    -0.07
    _precision
    -0.07
    Christian
    -0.07
    POSITIVE LOGITS
     asing
    0.09
     opin
    0.08
     thirds
    0.08
     fatigue
    0.08
     offshore
    0.08
     erupt
    0.08
     unfinished
    0.08
     incomplete
    0.08
    -six
    0.07
     준
    0.07
    Activations Density 0.002%

    No Known Activations