© 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. 68138
    Prev
    Next
    INDEX
    Explanations

    math formulas

    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
     Verte
    -0.08
     രണ്ടു
    -0.08
     Quaternion
    -0.08
     Laufe
    -0.08
     Platte
    -0.08
     أل
    -0.08
     completar
    -0.08
    妹
    -0.08
     Dean
    -0.07
     Limp
    -0.07
    POSITIVE LOGITS
    [i
    0.11
    _i
    0.10
     themselves
    0.09
     yourselves
    0.09
     individually
    0.09
    _owned
    0.09
     دخ
    0.08
     sínum
    0.08
     individuelles
    0.08
     audited
    0.08
    Activations Density 0.040%

    No Known Activations