© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 97280
    Prev
    Next
    INDEX
    Explanations

    S

    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
     sebel
    -0.09
     unen
    -0.08
     unsett
    -0.08
     kari
    -0.08
    ात्र
    -0.08
     vener
    -0.08
     noz
    -0.08
     enlever
    -0.08
    ateri
    -0.07
     Veget
    -0.07
    POSITIVE LOGITS
    ystème
    0.15
    out
    0.12
    yst
    0.12
    ’assurer
    0.11
    'assurer
    0.11
    UI
    0.10
    au
    0.10
    urtout
    0.10
    avo
    0.10
    urcharge
    0.10
    Activations Density 0.001%

    No Known Activations