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. 113026
    Prev
    Next
    INDEX
    Explanations

    ive

    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
    @Enable
    -0.08
     학생
    -0.07
    აი
    -0.07
     budou
    -0.07
     seront
    -0.07
    soon
    -0.07
     화
    -0.07
    uli
    -0.07
     보내
    -0.07
     Willem
    -0.07
    POSITIVE LOGITS
     Besten
    0.08
    NX
    0.08
     kink
    0.07
     contratar
    0.07
    KT
    0.07
    kona
    0.07
     csr
    0.07
     koox
    0.07
    CTX
    0.07
     বৃহ
    0.07
    Activations Density 0.000%

    No Known Activations