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. 11-RESID-POST-AA
    6. 106245
    Prev
    Next
    INDEX
    Explanations

    no

    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
     div
    -0.08
     fiscal
    -0.08
     Dabei
    -0.08
     Fuk
    -0.08
     ancestral
    -0.08
    .translation
    -0.07
     aumentando
    -0.07
     trac
    -0.07
     measurements
    -0.07
    増
    -0.07
    POSITIVE LOGITS
    Cant
    0.09
     alred
    0.09
     enclave
    0.09
    Fence
    0.08
     Cant
    0.08
     '/'↵
    0.08
    inu
    0.08
    PREC
    0.08
     fence
    0.08
    @Ng
    0.08
    Activations Density 0.025%

    No Known Activations