Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 470
    Prev
    Next
    INDEX
    Explanations

    thread

    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
    Ana
    -0.07
     Ao
    -0.07
    בות
    -0.07
    ес
    -0.07
    ergarten
    -0.07
    роме
    -0.07
     Mother
    -0.07
    ⁣
    -0.07
     garages
    -0.07
     absorber
    -0.07
    POSITIVE LOGITS
     Tit
    0.08
     titi
    0.08
    ień
    0.08
     naslov
    0.08
    TT
    0.08
     TT
    0.08
     పొ
    0.08
    482
    0.07
    WT
    0.07
    481
    0.07
    Activations Density 0.011%

    No Known Activations