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. 55923
    Prev
    Next
    INDEX
    Explanations

    parentheses, math expressions

    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
     ideally
    -0.08
     vorne
    -0.08
     Walter
    -0.08
     purpos
    -0.08
    ատ
    -0.08
    —as
    -0.07
    .intent
    -0.07
     इससे
    -0.07
    Messages
    -0.07
    -0.07
    POSITIVE LOGITS
    ``
    0.08
    úch
    0.07
    hide
    0.07
    Á
    0.07
    keyup
    0.07
    esh
    0.07
    cell
    0.07
    ตัว
    0.07
     HTC
    0.07
    啦
    0.07
    Activations Density 0.026%

    No Known Activations