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. 12187
    Prev
    Next
    INDEX
    Explanations

    policy

    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
     neçə
    -0.08
     Lazar
    -0.08
     Lucky
    -0.08
     Isabelle
    -0.08
    _dl
    -0.08
     Solaris
    -0.08
     dhacay
    -0.08
     RAID
    -0.08
     kacha
    -0.08
     ખુ
    -0.07
    POSITIVE LOGITS
    ofan
    0.08
     vape
    0.08
    Зап
    0.08
    '
    0.07
    afet
    0.07
     protections
    0.07
     fet
    0.07
     Зап
    0.07
     prohibition
    0.07
     смысл
    0.07
    Activations Density 0.006%

    No Known Activations