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. 102785
    Prev
    Next
    INDEX
    Explanations

    Fahrenheit 451, Rubik's cube

    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
     provision
    -0.08
     ^
    -0.08
     atop
    -0.08
     pase
    -0.07
     †
    -0.07
     Provision
    -0.07
    撮
    -0.07
     dessus
    -0.07
     Montgomery
    -0.07
     "=
    -0.07
    POSITIVE LOGITS
    Excluded
    0.09
     household
    0.09
     phenomenon
    0.08
     Household
    0.08
    icos
    0.08
     vastly
    0.08
     rotor
    0.08
     Turning
    0.08
    Desc
    0.08
     ris
    0.08
    Activations Density 0.005%

    No Known Activations