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. 111667
    Prev
    Next
    INDEX
    Explanations

    Greater than/equal to symbols

    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
    _EFFECT
    -0.08
     triturador
    -0.08
    Maker
    -0.08
    _resize
    -0.08
     terra
    -0.07
    _compile
    -0.07
    _effect
    -0.07
    602
    -0.07
    _encoder
    -0.07
    _hash
    -0.07
    POSITIVE LOGITS
     Marilyn
    0.08
     whisk
    0.08
    attie
    0.08
     weib
    0.08
     falling
    0.08
     percentile
    0.08
     breaches
    0.08
     failure
    0.08
    fällen
    0.08
     contamin
    0.08
    Activations Density 0.007%

    No Known Activations