© 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. 64984
    Prev
    Next
    INDEX
    Explanations

    at

    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
     homeschool
    -0.07
     essais
    -0.07
     СН
    -0.07
     rf
    -0.07
     analytical
    -0.07
     Firefox
    -0.07
    リエ
    -0.07
    -needed
    -0.07
     científica
    -0.07
     Los
    -0.07
    POSITIVE LOGITS
     విద
    0.09
    Foreign
    0.08
     lor
    0.08
    .Foreign
    0.08
    -era
    0.08
     foreign
    0.08
     иностран
    0.08
    (graph
    0.08
     خارجی
    0.08
     विदेशी
    0.08
    Activations Density 0.004%

    No Known Activations