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. 7-RESID-POST-AA
    6. 1825
    Prev
    Next
    INDEX
    Explanations

    ney

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CRC
    -0.08
    ihar
    -0.08
    �
    -0.08
     toe
    -0.08
     CRC
    -0.08
     tariffs
    -0.07
     autoestima
    -0.07
    illary
    -0.07
    .Var
    -0.07
     adapte
    -0.07
    POSITIVE LOGITS
     przede
    0.08
     вел
    0.07
    Yeah
    0.07
    xygen
    0.07
    زيادة
    0.07
     zau
    0.07
     Enhanced
    0.07
     الموجود
    0.07
     vele
    0.07
     cibl
    0.07
    Activations Density 0.009%

    No Known Activations