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

    Neuronpedia

    APICircuit 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. 53999
    Prev
    Next
    INDEX
    Explanations

    point

    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
     paced
    -0.09
    ISH
    -0.09
    promo
    -0.09
    WN
    -0.08
    interactive
    -0.08
    Nick
    -0.08
    leader
    -0.08
    xor
    -0.08
    ATOR
    -0.08
     curios
    -0.07
    POSITIVE LOGITS
     hij
    0.09
     далеко
    0.08
     Begin
    0.08
     happy
    0.07
     связ
    0.07
    اران
    0.07
     pressup
    0.07
     genoemd
    0.07
    ارہ
    0.07
    .hu
    0.07
    Activations Density 0.001%

    No Known Activations