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. 48365
    Prev
    Next
    INDEX
    Explanations

    Microsoft

    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
     scar
    -0.09
    ogenic
    -0.08
     trate
    -0.08
     star
    -0.08
     Agen
    -0.08
    星
    -0.08
     embracing
    -0.08
     iedereen
    -0.08
     星
    -0.07
     ench
    -0.07
    POSITIVE LOGITS
    cker
    0.07
     rind
    0.07
     ত
    0.07
     pey
    0.07
    ُّ
    0.07
    ({_
    0.07
     damar
    0.07
    ‌توانید
    0.07
    ুঁজ
    0.07
     المس
    0.07
    Activations Density 0.004%

    No Known Activations