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. 104088
    Prev
    Next
    INDEX
    Explanations

    view

    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
     ;-
    -0.08
     نرم
    -0.08
     맞
    -0.08
     افزار
    -0.08
     فناوری
    -0.08
     کاهش
    -0.08
     نواز
    -0.07
     vocês
    -0.07
     محور
    -0.07
     perquè
    -0.07
    POSITIVE LOGITS
    ensione
    0.08
    -uppercase
    0.08
     specialized
    0.08
     bijzonder
    0.07
    alternative
    0.07
    167
    0.07
    نك
    0.07
    881
    0.07
    /edit
    0.07
     Mens
    0.07
    Activations Density 0.024%

    No Known Activations