© 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. 11-RESID-POST-AA
    11. 599
    Prev
    Next
    INDEX
    Explanations

    moisture

    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
     nég
    -0.08
     afet
    -0.08
     verkla
    -0.08
     auton
    -0.08
     భ
    -0.07
     tror
    -0.07
     ముగ
    -0.07
     tirer
    -0.07
     noen
    -0.07
     IBM
    -0.07
    POSITIVE LOGITS
     менедж
    0.09
     постоян
    0.09
    -producing
    0.08
     throughout
    0.08
    Prepar
    0.08
     continuously
    0.08
    Providing
    0.08
    Continu
    0.08
    =$_
    0.08
    Continuous
    0.08
    Activations Density 0.005%

    No Known Activations