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. 9079
    Prev
    Next
    INDEX
    Explanations

    brow/brown

    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
    筑
    -0.09
     airtight
    -0.08
    typed
    -0.08
    _rest
    -0.07
     priced
    -0.07
     बद
    -0.07
    TK
    -0.07
    "|
    -0.07
     बुल
    -0.07
    aph
    -0.07
    POSITIVE LOGITS
     появ
    0.08
     اللون
    0.08
    ające
    0.08
    /red
    0.08
     luce
    0.07
     LEDs
    0.07
     renk
    0.07
     appearing
    0.07
     pouvant
    0.07
     rind
    0.07
    Activations Density 0.002%

    No Known Activations