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. 58974
    Prev
    Next
    INDEX
    Explanations

    the

    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
     Demokr
    -0.08
     Ár
    -0.08
     við
    -0.07
    审核
    -0.07
    חים
    -0.07
    ueblos
    -0.07
     traces
    -0.07
    Ee
    -0.07
    框
    -0.07
    Boxes
    -0.07
    POSITIVE LOGITS
     despert
    0.09
     streamline
    0.08
     Wake
    0.08
     waking
    0.08
    тан
    0.08
    άλ
    0.08
     wake
    0.08
    atten
    0.08
    .rad
    0.08
     энерг
    0.08
    Activations Density 0.002%

    No Known Activations