Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 112016
    Prev
    Next
    INDEX
    Explanations

    two-factor authentication & security

    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
     मैथ
    -0.08
     Commissie
    -0.08
     imperial
    -0.07
    mounted
    -0.07
     arfer
    -0.07
     שעה
    -0.07
    ער
    -0.07
     三
    -0.07
     pib
    -0.07
    بية
    -0.07
    POSITIVE LOGITS
    aps
    0.09
    apsulation
    0.09
    llu
    0.09
    _sig
    0.08
    ord
    0.08
     rejecting
    0.08
    APS
    0.07
    _rates
    0.07
    avelength
    0.07
    Rejected
    0.07
    Activations Density 0.000%

    No Known Activations