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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 1594
    Prev
    Next
    INDEX
    Explanations

    tumble

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _alert
    -0.08
     Alerts
    -0.08
     alerta
    -0.08
     Lys
    -0.07
    -alert
    -0.07
     ridiculous
    -0.07
     이벤트
    -0.07
    alert
    -0.07
    _cli
    -0.07
    _allocator
    -0.07
    POSITIVE LOGITS
     tumble
    0.08
     sometime
    0.08
    Field
    0.07
     Kron
    0.07
     witness
    0.07
     milestones
    0.07
     buna
    0.07
    ума
    0.07
     tire
    0.07
     oz
    0.07
    Activations Density 0.002%

    No Known Activations