© 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. 99280
    Prev
    Next
    INDEX
    Explanations

    research methods

    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
    _AS
    -0.08
     mencapai
    -0.08
     menik
    -0.08
    -most
    -0.08
    _ALWAYS
    -0.07
    925
    -0.07
     Anyways
    -0.07
    皇
    -0.07
    开始
    -0.07
    _NON
    -0.07
    POSITIVE LOGITS
     examining
    0.13
     examine
    0.12
     interviews
    0.11
     examination
    0.11
     examines
    0.11
     Examine
    0.11
     comparing
    0.11
     Examination
    0.10
     beobachten
    0.10
     Interviews
    0.10
    Activations Density 0.032%

    No Known Activations