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. 111610
    Prev
    Next
    INDEX
    Explanations

    medical tests

    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
    精选
    -0.10
     kese
    -0.09
    经典
    -0.08
    jale
    -0.08
    精彩
    -0.08
    _CUSTOM
    -0.08
     yearning
    -0.08
    _BROWSER
    -0.08
    zad
    -0.08
    ▫
    -0.08
    POSITIVE LOGITS
     interfering
    0.13
     contamination
    0.11
     unrelated
    0.11
     falsely
    0.11
     interference
    0.11
     interfere
    0.10
    ामुळे
    0.10
     contamin
    0.10
    noise
    0.10
    urious
    0.10
    Activations Density 0.027%

    No Known Activations