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. 11800
    Prev
    Next
    INDEX
    Explanations

    answer

    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
     respecting
    -0.08
    firm
    -0.07
     Sho
    -0.07
    olt
    -0.07
     Srin
    -0.07
     Sey
    -0.07
     tent
    -0.07
     �
    -0.07
    ish
    -0.07
     Beat
    -0.07
    POSITIVE LOGITS
    მის
    0.09
     divina
    0.08
    מע
    0.08
     charisma
    0.08
     Limb
    0.08
     limb
    0.07
    aque
    0.07
    ​ត
    0.07
    工作人员
    0.07
     없어
    0.07
    Activations Density 0.084%

    No Known Activations