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

    Neuronpedia

    APICircuit 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. 15-RESID-POST-AA
    6. 155
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _literal
    -0.10
    "x
    -0.09
    _mul
    -0.09
    (layer
    -0.09
    _eval
    -0.09
    ;//
    -0.09
    _attach
    -0.09
     plethora
    -0.08
    _eq
    -0.08
    ysql
    -0.08
    POSITIVE LOGITS
     the
    0.09
     equipment
    0.09
     it
    0.08
     Gujarat
    0.08
     Chennai
    0.08
     on
    0.07
     through
    0.07
     Cebu
    0.07
     Rock
    0.07
     supposedly
    0.07
    Activations Density 0.063%

    No Known Activations