© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 96843
    Prev
    Next
    INDEX
    Explanations

    C

    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
    ards
    -0.08
    aliland
    -0.08
    uerda
    -0.08
    ands
    -0.07
    ename
    -0.07
    akı
    -0.07
     hired
    -0.07
    wid
    -0.07
    ę
    -0.07
    anders
    -0.07
    POSITIVE LOGITS
     granito
    0.10
    成熟
    0.09
     manufacturing
    0.09
    ynthesis
    0.09
     دليل
    0.08
    نی
    0.08
     عملی
    0.08
     anspruch
    0.08
     مرحله
    0.08
     conserva
    0.08
    Activations Density 0.007%

    No Known Activations