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. 29870
    Prev
    Next
    INDEX
    Explanations

    endre

    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
     hav
    -0.07
     Wins
    -0.07
    镇
    -0.07
     Cim
    -0.07
    醒
    -0.07
     Herc
    -0.07
     gladi
    -0.07
     med
    -0.07
    clin
    -0.07
    оглас
    -0.07
    POSITIVE LOGITS
     વ્યક્ત
    0.08
     '?'
    0.08
     ild
    0.08
     izraz
    0.08
     divul
    0.08
     practition
    0.07
    fragen
    0.07
    _EXP
    0.07
     voc
    0.07
     government's
    0.07
    Activations Density 0.001%

    No Known Activations