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. 11-RESID-POST-AA
    6. 43333
    Prev
    Next
    INDEX
    Explanations

    )

    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
     conjunction
    -0.09
     variations
    -0.08
     forefront
    -0.08
     correl
    -0.08
     claims
    -0.07
     covenant
    -0.07
    Variants
    -0.07
    (varargin
    -0.07
     variants
    -0.07
    طط
    -0.07
    POSITIVE LOGITS
     Danach
    0.10
     ואז
    0.09
    .follow
    0.09
     '['
    0.09
     retourn
    0.08
     Betrag
    0.08
     Haben
    0.08
     промеж
    0.08
    返回
    0.08
     返回
    0.08
    Activations Density 0.037%

    No Known Activations