© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 48498
    Prev
    Next
    INDEX
    Explanations

    string

    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
     profesión
    -0.09
     professionelle
    -0.08
     profesjonal
    -0.08
     праф
    -0.08
     professionnel
    -0.07
     professionals
    -0.07
     מקצוע
    -0.07
     professioneel
    -0.07
     profissional
    -0.07
     profesional
    -0.07
    POSITIVE LOGITS
     string
    0.74
    字符串
    0.72
    _string
    0.65
    string
    0.64
     문자열
    0.64
    String
    0.63
     String
    0.62
    .string
    0.62
    -string
    0.62
    	string
    0.61
    Activations Density 0.254%

    No Known Activations