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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 113058
    Prev
    Next
    INDEX
    Explanations

    Psalm 23

    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
    าห
    -0.08
     rete
    -0.08
     सामग्री
    -0.08
     targeting
    -0.07
     купить
    -0.07
     Nancy
    -0.07
     mobil
    -0.07
     Several
    -0.07
     synthesized
    -0.07
     synth
    -0.07
    POSITIVE LOGITS
    І
    0.08
     Jehová
    0.08
     LORD
    0.08
    ��
    0.08
     companionship
    0.08
     woods
    0.08
    WS
    0.08
     Hills
    0.08
     eaux
    0.08
     WITH
    0.08
    Activations Density 0.010%

    No Known Activations