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. 65249
    Prev
    Next
    INDEX
    Explanations

    code, language, technical

    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
     HY
    -0.11
    .seconds
    -0.09
    HY
    -0.09
     punished
    -0.09
    arsch
    -0.08
    Kenzie
    -0.08
     hikari
    -0.08
    的发展
    -0.08
    որը
    -0.08
     prejud
    -0.08
    POSITIVE LOGITS
    ORM
    0.07
     profite
    0.07
     மெ
    0.07
     format
    0.07
     downstream
    0.07
    Dll
    0.07
    format
    0.06
    Ont
    0.06
     Regard
    0.06
     als
    0.06
    Activations Density 0.000%

    No Known Activations