© 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. 11-RESID-POST-AA
    11. 100
    Prev
    Next
    INDEX
    Explanations

    along

    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
     altında
    -0.08
    (issue
    -0.08
    _DIP
    -0.07
     다음
    -0.07
     maje
    -0.07
     �
    -0.07
     sest
    -0.07
    spunkt
    -0.07
    .processor
    -0.07
     descanso
    -0.07
    POSITIVE LOGITS
    ground
    0.08
    cover
    0.08
    covers
    0.07
    outer
    0.07
     uninterrupted
    0.07
     collar
    0.07
     Forgotten
    0.07
     urged
    0.07
     confines
    0.07
    locked
    0.07
    Activations Density 0.017%

    No Known Activations