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. 65480
    Prev
    Next
    INDEX
    Explanations

    inquiry

    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
    ullar
    -0.07
    ampang
    -0.07
     Antarctica
    -0.07
     organizational
    -0.07
    ull
    -0.07
    ırlar
    -0.07
    uliar
    -0.07
     pit
    -0.07
    ाउंट
    -0.07
    иболее
    -0.07
    POSITIVE LOGITS
     AGAIN
    0.09
     PREC
    0.08
    VERS
    0.08
     Atlas
    0.08
    double
    0.08
     REQUIRE
    0.08
    rero
    0.08
     Vä
    0.08
     �
    0.07
     Norton
    0.07
    Activations Density 0.000%

    No Known Activations