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. 23-RESID-POST-AA
    6. 98583
    Prev
    Next
    INDEX
    Explanations

    satisfaction

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nota
    -0.08
     coneg
    -0.08
     suspect
    -0.08
    ಕ್ಟ
    -0.08
     cuch
    -0.08
    andika
    -0.08
     eint
    -0.07
     crashing
    -0.07
     inevitable
    -0.07
    सर
    -0.07
    POSITIVE LOGITS
    weis
    0.09
    fac
    0.09
    azioni
    0.09
    ak
    0.08
    face
    0.08
    izo
    0.08
    tru
    0.08
     visage
    0.08
    akc
    0.08
    fa
    0.08
    Activations Density 0.000%

    No Known Activations