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. 98393
    Prev
    Next
    INDEX
    Explanations

    say "out"

    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
    Occurs
    -0.09
    Out
    -0.09
    Dónde
    -0.08
    Applic
    -0.08
    Kont
    -0.08
    Til
    -0.08
    utsche
    -0.08
    нера
    -0.08
    Occ
    -0.08
    NSNotification
    -0.08
    POSITIVE LOGITS
     Number
    0.10
     Score
    0.08
    _scores
    0.08
    _score
    0.08
    	Value
    0.08
     πο
    0.07
     Value
    0.07
     ẹ
    0.07
     [
    0.07
    ښو
    0.07
    Activations Density 0.000%

    No Known Activations