© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 48599
    Prev
    Next
    INDEX
    Explanations

    呈

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .fm
    -0.08
    awule
    -0.08
     competências
    -0.08
     Scheduling
    -0.07
     हल
    -0.07
    .par
    -0.07
    .ec
    -0.07
     hobby
    -0.07
     Enforcement
    -0.07
     Lös
    -0.07
    POSITIVE LOGITS
    递
    0.10
    ゼント
    0.10
    献
    0.10
    现实
    0.10
    output
    0.10
    outputs
    0.09
    র্শ
    0.09
    interaction
    0.08
     realist
    0.08
    시
    0.08
    Activations Density 0.001%

    No Known Activations