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

    Neuronpedia

    APICircuit 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. 23-RESID-POST-AA
    6. 130885
    Prev
    Next
    INDEX
    Explanations

    say the hyphen

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    68
    -0.09
    15
    -0.09
    elsius
    -0.08
    's
    -0.08
    ahrenheit
    -0.08
    akuwa
    -0.08
    ১৫
    -0.08
    १५
    -0.08
    ancé
    -0.08
    85
    -0.08
    POSITIVE LOGITS
     lengths
    0.13
    nodes
    0.12
     nodes
    0.11
    _lengths
    0.11
    Nodes
    0.11
    items
    0.11
    _nodes
    0.11
    length
    0.11
     размеров
    0.11
    _items
    0.11
    Activations Density 0.164%

    No Known Activations