© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 96452
    Prev
    Next
    INDEX
    Explanations

    767

    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
     flash
    -0.09
     Flash
    -0.09
    Flash
    -0.08
    cr
    -0.08
    _behavior
    -0.07
    ia
    -0.07
    char
    -0.07
     behavior
    -0.07
    flash
    -0.07
    illiams
    -0.07
    POSITIVE LOGITS
     começo
    0.09
     այն
    0.09
     început
    0.09
     �
    0.08
    ụọ
    0.08
    étaire
    0.08
    ébergement
    0.08
     editing
    0.08
    umanité
    0.08
     ποι
    0.08
    Activations Density 0.000%

    No Known Activations