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. 102916
    Prev
    Next
    INDEX
    Explanations

    steps

    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
     tas
    -0.09
     туал
    -0.08
     taşı
    -0.07
    Tas
    -0.07
     એપ
    -0.07
    ဂ
    -0.07
     Tas
    -0.07
    ordam
    -0.07
     চিকিৎস
    -0.07
     dimensión
    -0.07
    POSITIVE LOGITS
    ्ती
    0.08
    /H
    0.08
    0.08
     Mets
    0.08
     stappen
    0.07
     विध
    0.07
    HV
    0.07
    chaft
    0.07
     kort
    0.07
    ್ಮ
    0.07
    Activations Density 0.004%

    No Known Activations