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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 12783
    Prev
    Next
    INDEX
    Explanations

    punctuation, conjunctions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Patagonia
    -0.08
    uscht
    -0.07
     tote
    -0.07
     pit
    -0.07
     Jogos
    -0.07
    제품
    -0.07
     Rei
    -0.07
     Finanzierung
    -0.07
     Creo
    -0.07
    xty
    -0.07
    POSITIVE LOGITS
     jää
    0.08
    'Am
    0.08
     vee
    0.08
     gig
    0.07
    叉
    0.07
     vrou
    0.07
     उ
    0.07
     blader
    0.07
    hran
    0.07
    meid
    0.07
    Activations Density 0.000%

    No Known Activations