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. 3-RESID-POST-AA
    6. 1669
    Prev
    Next
    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     труда
    -0.09
     subst
    -0.08
    imonio
    -0.08
     อ
    -0.07
     것
    -0.07
     dre
    -0.07
     spokesperson
    -0.07
    ล
    -0.07
     привести
    -0.07
     Staffing
    -0.07
    POSITIVE LOGITS
    骤
    0.08
     ott
    0.08
     cren
    0.07
     Rift
    0.07
     Gest
    0.07
     Boni
    0.07
     geometr
    0.07
    Sensor
    0.07
     entre
    0.07
    兄
    0.07
    Activations Density 0.000%

    No Known Activations