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. 111868
    Prev
    Next
    INDEX
    Explanations

    unparsable text

    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
     బె
    -0.09
     stok
    -0.09
    -0.08
    ognitive
    -0.08
     stools
    -0.08
     Fritz
    -0.08
     dean
    -0.08
     Bull
    -0.08
     ceeb
    -0.08
     극
    -0.08
    POSITIVE LOGITS
    _Channel
    0.08
    ver
    0.08
    CHAN
    0.07
    Coe
    0.07
     Canal
    0.07
    _decoder
    0.07
    ó
    0.07
     int
    0.07
    agma
    0.07
    _co
    0.07
    Activations Density 0.001%

    No Known Activations