Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 111815
    Prev
    Next
    INDEX
    Explanations

    as

    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
    URED
    -0.09
     skull
    -0.08
    urons
    -0.07
     ore
    -0.07
     lob
    -0.07
    ured
    -0.07
     prec
    -0.07
    ures
    -0.07
    omt
    -0.07
     accomplished
    -0.07
    POSITIVE LOGITS
    以下简称
    0.09
    简称
    0.09
    *b
    0.08
     berp
    0.08
    akin
    0.08
     bapt
    0.07
     _)
    0.07
     вуз
    0.07
     Spi
    0.07
     сәй
    0.07
    Activations Density 0.001%

    No Known Activations