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. 11-RESID-POST-AA
    6. 30138
    Prev
    Next
    INDEX
    Explanations

    mathematical proofs

    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
    _tables
    -0.08
    -0.08
    _caption
    -0.08
     sommes
    -0.08
     neglected
    -0.08
    caption
    -0.08
    안을
    -0.08
     calculations
    -0.08
    calcul
    -0.08
     propor
    -0.08
    POSITIVE LOGITS
     footh
    0.09
     spanning
    0.08
    .stop
    0.08
     Stop
    0.07
     જાણ
    0.07
     dauerhaft
    0.07
     професс
    0.07
    停止
    0.07
    	stop
    0.07
     inger
    0.07
    Activations Density 0.014%

    No Known Activations