© 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. 108621
    Prev
    Next
    INDEX
    Explanations

    sideways movement

    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
     rules
    -0.09
     Rules
    -0.08
     règles
    -0.08
    Rules
    -0.08
    .rules
    -0.08
     rule
    -0.08
     verses
    -0.08
     waters
    -0.07
     regras
    -0.07
     partout
    -0.07
    POSITIVE LOGITS
     deviation
    0.14
     desvi
    0.14
    Deviation
    0.13
    方向
    0.12
     sideways
    0.12
     방향
    0.12
     deviations
    0.11
     devi
    0.11
     corrective
    0.11
     направлении
    0.11
    Activations Density 0.023%

    No Known Activations