© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 29703
    Prev
    Next
    INDEX
    Explanations

    Medical treatments, biological substances

    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
    (write
    -0.08
     Intelligence
    -0.08
     monarchy
    -0.08
     RAF
    -0.08
     intelligence
    -0.07
     igihugu
    -0.07
     нем
    -0.07
    (ma
    -0.07
    (matrix
    -0.07
    ätte
    -0.07
    POSITIVE LOGITS
     �
    0.08
    缺
    0.07
    SPACE
    0.07
    _DUP
    0.07
     Athlete
    0.07
     VIS
    0.07
     cue
    0.07
    BUS
    0.07
     fuzz
    0.07
    VIS
    0.07
    Activations Density 0.000%

    No Known Activations