© 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. 11-RESID-POST-AA
    11. 75439
    Prev
    Next
    INDEX
    Explanations

    computer code snippets

    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
    llt
    -0.09
     πάν
    -0.09
     NTN
    -0.08
    Kh
    -0.08
     истории
    -0.08
     kukho
    -0.08
     kt
    -0.08
    чим
    -0.08
    kok
    -0.08
     лишь
    -0.08
    POSITIVE LOGITS
     específicos
    0.08
     Break
    0.08
     sagen
    0.08
     misuse
    0.08
    _file
    0.07
     spécifiques
    0.07
    0.07
    _break
    0.07
    ્મ
    0.07
    Break
    0.07
    Activations Density 0.001%
    No Known Activations