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. 7-RESID-POST-AA
    6. 1747
    Prev
    Next
    INDEX
    Explanations

    Instructions and tips

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    जर
    -0.07
    दिल
    -0.07
     airplanes
    -0.07
    esch
    -0.07
     restraint
    -0.07
     Trink
    -0.07
     geb
    -0.07
     checker
    -0.07
    જ
    -0.07
    हे
    -0.07
    POSITIVE LOGITS
    -picked
    0.08
    &gt
    0.08
     sif
    0.08
    slam
    0.08
     upl
    0.07
     elk
    0.07
    øl
    0.07
    -pot
    0.07
    .demo
    0.07
     sift
    0.07
    Activations Density 0.410%

    No Known Activations