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. 11-RESID-POST-AA
    6. 113935
    Prev
    Next
    INDEX
    Explanations

    of

    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
    െയ്
    -0.09
     jargon
    -0.09
     ضمن
    -0.08
     કરતી
    -0.08
    Nation
    -0.07
     materials
    -0.07
    Fo
    -0.07
    ýan
    -0.07
    жи
    -0.07
    ienti
    -0.07
    POSITIVE LOGITS
     Hardy
    0.09
     desigual
    0.08
     NOT
    0.08
     vin
    0.08
     ambos
    0.07
    quare
    0.07
     nota
    0.07
     diagon
    0.07
     ак
    0.07
     undir
    0.07
    Activations Density 0.004%

    No Known Activations