© 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. 7-RESID-POST-AA
    11. 1471
    Prev
    Next
    INDEX
    Explanations

    random

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :g
    -0.08
     بالخ
    -0.08
     jüng
    -0.08
     стране
    -0.07
     zicht
    -0.07
     свид
    -0.07
     cale
    -0.07
     jal
    -0.07
     어
    -0.07
     zucchini
    -0.07
    POSITIVE LOGITS
     addresses
    0.08
    oplan
    0.08
    CORD
    0.08
     TABLE
    0.08
    Շ
    0.07
     வருகின்ற
    0.07
    вр
    0.07
    Та
    0.07
    ने
    0.07
     Շ
    0.07
    Activations Density 0.001%

    No Known Activations