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. 48392
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
     harmonic
    -0.10
    notations
    -0.07
     Laws
    -0.07
     notation
    -0.07
    (Content
    -0.07
    aatst
    -0.07
    ogar
    -0.07
     Harm
    -0.07
    reasonable
    -0.07
     ক্য
    -0.07
    POSITIVE LOGITS
    jour
    0.09
    \Event
    0.08
     viaje
    0.08
     വിട
    0.08
     jestem
    0.08
     unsolicited
    0.08
    @gmail
    0.08
     қал
    0.07
     bry
    0.07
     Владим
    0.07
    Activations Density 0.006%

    No Known Activations