© 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. 48050
    Prev
    Next
    INDEX
    Explanations

    Code snippets and instructions

    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
    88
    -0.08
    rey
    -0.08
    -bound
    -0.08
    86
    -0.07
    ieli
    -0.07
    oston
    -0.07
     Quy
    -0.07
     bound
    -0.07
    ay
    -0.07
     eğitim
    -0.07
    POSITIVE LOGITS
    pl
    0.09
     प्ल
    0.09
    ыч
    0.08
     panes
    0.08
    лис
    0.08
     প্ল
    0.08
     પ્લ
    0.08
     geben
    0.08
    [str
    0.07
    firmasi
    0.07
    Activations Density 0.000%

    No Known Activations