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. 113936
    Prev
    Next
    INDEX
    Explanations

    per

    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
    letion
    -0.09
     dich
    -0.08
    Lister
    -0.07
     entde
    -0.07
    ermi
    -0.07
    /FM
    -0.07
    ವನ
    -0.07
    Lees
    -0.07
     Lees
    -0.07
     stuff
    -0.07
    POSITIVE LOGITS
     mayo
    0.08
     noop
    0.08
    atele
    0.08
     iguales
    0.08
     dozen
    0.08
    jük
    0.07
    386
    0.07
     nop
    0.07
    659
    0.07
    ijnlijk
    0.07
    Activations Density 0.010%

    No Known Activations