© 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. 64994
    Prev
    Next
    INDEX
    Explanations

    Pro

    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
     syscall
    -0.11
     UNIX
    -0.11
     gzip
    -0.10
     Unix
    -0.10
     anthology
    -0.09
    Policies
    -0.09
    Unix
    -0.09
     gamble
    -0.09
     Occupational
    -0.09
     snprintf
    -0.09
    POSITIVE LOGITS
     geometry
    0.13
    _angle
    0.12
     planar
    0.12
     angles
    0.11
    -angle
    0.11
     geometr
    0.11
    Angle
    0.11
     geometric
    0.11
     Steiner
    0.11
     triangles
    0.10
    Activations Density 0.177%

    No Known Activations