Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 19087
    Prev
    Next
    INDEX
    Explanations

    technical specifications

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lokal
    -0.07
     సూచ
    -0.07
     impres
    -0.07
     missing
    -0.07
     destaca
    -0.07
    شكل
    -0.07
     which
    -0.07
     ಸೂಚ
    -0.07
     destac
    -0.07
     subject
    -0.07
    POSITIVE LOGITS
    bé
    0.09
    Interactions
    0.09
     fonctionnalités
    0.09
    young
    0.08
    roidism
    0.08
     opérations
    0.08
    ',"
    0.08
    beans
    0.08
    fuck
    0.08
    urias
    0.08
    Activations Density 0.117%

    No Known Activations