© 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. 78845
    Prev
    Next
    INDEX
    Explanations

    math symbols

    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
    angrijk
    -0.07
    'han
    -0.07
     Release
    -0.07
    .which
    -0.07
    INUX
    -0.07
     very
    -0.07
    <stdio
    -0.07
    @end
    -0.07
    ishing
    -0.07
     mau
    -0.07
    POSITIVE LOGITS
    half
    0.11
     half
    0.10
     halves
    0.10
    Half
    0.09
     Hälfte
    0.09
    _half
    0.09
     노력
    0.09
     полов
    0.09
    _HALF
    0.09
     Half
    0.09
    Activations Density 0.136%

    No Known Activations