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. 102800
    Prev
    Next
    INDEX
    Explanations

    chemistry

    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
     Vision
    -0.08
     vista
    -0.08
     limit
    -0.08
    _VIEW
    -0.08
     visibility
    -0.07
     vision
    -0.07
    .limit
    -0.07
     verksam
    -0.07
     surfing
    -0.07
     verdict
    -0.07
    POSITIVE LOGITS
    atomic
    0.10
     atomic
    0.09
     атом
    0.09
    (atom
    0.08
     Atomic
    0.08
    possible
    0.08
    昂
    0.08
    _atom
    0.08
     Koe
    0.08
     الكيمي
    0.08
    Activations Density 0.011%

    No Known Activations