© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 47855
    Prev
    Next
    INDEX
    Explanations

    Fire

    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
     faithful
    -0.07
     stump
    -0.07
    Dirty
    -0.07
     pav
    -0.07
     pavement
    -0.07
     wash
    -0.07
     Ew
    -0.07
    ↵                    ↵
    -0.07
    ubi
    -0.07
     pun
    -0.06
    POSITIVE LOGITS
    walls
    0.09
    works
    0.08
    fighters
    0.08
    power
    0.08
    Works
    0.08
     Alfonso
    0.07
    /AIDS
    0.07
    truck
    0.07
     lidi
    0.07
    ball
    0.07
    Activations Density 0.023%

    No Known Activations