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. 15-RESID-POST-AA
    6. 19456
    Prev
    Next
    INDEX
    Explanations

    Non-English words

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cen
    -0.07
     Ariel
    -0.07
    árl
    -0.07
    .AUTH
    -0.07
     ressemble
    -0.07
     Xavier
    -0.07
     Enrollment
    -0.07
     Są
    -0.07
     Salem
    -0.07
     securing
    -0.07
    POSITIVE LOGITS
     ýok
    0.09
    אריך
    0.09
    יגע
    0.08
    roffene
    0.08
    Investig
    0.08
    Timestamp
    0.08
    GH
    0.08
     dichas
    0.08
     дээ
    0.08
     вами
    0.08
    Activations Density 0.000%

    No Known Activations