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. 53825
    Prev
    Next
    INDEX
    Explanations

    Molting

    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
     Favourite
    -0.08
     Query
    -0.07
     Governors
    -0.07
     Manhattan
    -0.07
    ুকে
    -0.07
     Seen
    -0.07
    -0.07
     grilling
    -0.07
     Proven
    -0.07
     Accident
    -0.06
    POSITIVE LOGITS
     molt
    0.13
     molts
    0.13
    transition
    0.11
     संक्रमण
    0.11
     시즌
    0.11
     overgang
    0.10
     зрел
    0.10
     परिवर्तन
    0.10
     transformative
    0.10
    -stage
    0.10
    Activations Density 0.005%

    No Known Activations