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. 12014
    Prev
    Next
    INDEX
    Explanations

    Legal agreement terms

    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
    ologo
    -0.09
     Evo
    -0.08
    egenomen
    -0.08
    scode
    -0.08
    ίζεται
    -0.07
     Res
    -0.07
     explained
    -0.07
    χύ
    -0.07
     sentiment
    -0.07
     Hintergrund
    -0.07
    POSITIVE LOGITS
     junction
    0.08
     pact
    0.08
     lé
    0.08
     disagreements
    0.08
     accidentally
    0.08
    Ownership
    0.08
     inadvert
    0.08
     improperly
    0.08
     toget
    0.08
     amendments
    0.08
    Activations Density 0.002%

    No Known Activations