Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 76127
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
     therapist
    -0.09
     hypnosis
    -0.09
     diagnosed
    -0.09
     presencial
    -0.09
    Dragging
    -0.08
     psychologist
    -0.08
    \Route
    -0.08
    Instructor
    -0.08
     therapists
    -0.08
    -rated
    -0.08
    POSITIVE LOGITS
     enormous
    0.14
     huge
    0.12
     billions
    0.12
     enormes
    0.12
     trillion
    0.12
     billion
    0.11
     gigantic
    0.11
     Huge
    0.11
     colossal
    0.11
     Milliarden
    0.11
    Activations Density 0.076%

    No Known Activations