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. 65718
    Prev
    Next
    INDEX
    Explanations

    False reports/hoaxes

    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
     дополн
    -0.09
     ships
    -0.08
    /profile
    -0.08
     relationships
    -0.07
    -any
    -0.07
     relatable
    -0.07
    /os
    -0.07
    /share
    -0.07
     память
    -0.07
    収納
    -0.07
    POSITIVE LOGITS
    fake
    0.10
     fake
    0.10
     trainen
    0.09
     التدريب
    0.09
     പരിശീല
    0.09
     falsa
    0.09
     falso
    0.09
     તાલ
    0.09
     ಸುದ್ದ
    0.09
     treinamento
    0.09
    Activations Density 0.031%

    No Known Activations