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. 49018
    Prev
    Next
    INDEX
    Explanations

    in

    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
    Calls
    -0.08
    Call
    -0.08
    .calls
    -0.08
     cron
    -0.08
     caller
    -0.08
    انات
    -0.08
     administrador
    -0.07
    _call
    -0.07
    izr
    -0.07
     siebie
    -0.07
    POSITIVE LOGITS
    _pixels
    0.10
     QUEST
    0.09
    Pixels
    0.09
     Pixels
    0.09
    pixel
    0.08
    pixels
    0.08
     Pixel
    0.08
     pix
    0.08
    _pixel
    0.08
     जेल
    0.07
    Activations Density 0.002%

    No Known Activations