© 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. 31049
    Prev
    Next
    INDEX
    Explanations

    Visual field

    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
    _bonus
    -0.09
    lub
    -0.08
    hero
    -0.08
     unnatural
    -0.08
     drill
    -0.08
    /dr
    -0.07
    -dr
    -0.07
    floating
    -0.07
    ulik
    -0.07
     label
    -0.07
    POSITIVE LOGITS
     molts
    0.09
    inum
    0.09
     molt
    0.09
     beiden
    0.09
     Torres
    0.09
    (Screen
    0.08
    .qt
    0.08
     meste
    0.08
     mapas
    0.08
    itudes
    0.08
    Activations Density 0.002%

    No Known Activations