© 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. 11-RESID-POST-AA
    6. 8134
    Prev
    Next
    INDEX
    Explanations

    att

    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
    재
    -0.08
     Tk
    -0.07
     XII
    -0.07
     holding
    -0.07
     Sik
    -0.07
     Dict
    -0.07
     Vivi
    -0.07
    edis
    -0.07
     style
    -0.07
     নির
    -0.07
    POSITIVE LOGITS
    reau
    0.08
    ANDO
    0.08
    Threshold
    0.08
     terraces
    0.08
     넘어
    0.08
     opgelost
    0.08
    poort
    0.08
     odpor
    0.08
     slapped
    0.08
    prowadz
    0.07
    Activations Density 0.000%

    No Known Activations