© 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. 96927
    Prev
    Next
    INDEX
    Explanations

    Phot

    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
    illator
    -0.08
    eliz
    -0.08
     المسلحة
    -0.08
     тр
    -0.08
     touching
    -0.08
     analyzer
    -0.08
    issuer
    -0.07
    anelo
    -0.07
    gerald
    -0.07
    elyn
    -0.07
    POSITIVE LOGITS
    845
    0.08
     vaihe
    0.08
    0.08
     zake
    0.08
    $s
    0.08
    idding
    0.07
    Requests
    0.07
     Bok
    0.07
    Repeated
    0.07
    كو
    0.07
    Activations Density 0.001%

    No Known Activations