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. 60554
    Prev
    Next
    INDEX
    Explanations

    get

    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
     REM
    -0.08
     Rash
    -0.07
     Telef
    -0.07
     Parm
    -0.07
     folded
    -0.07
    ом
    -0.07
     LAST
    -0.07
     Min
    -0.07
     cenu
    -0.07
     signed
    -0.07
    POSITIVE LOGITS
    くだ
    0.08
     اللازمة
    0.08
     ஐ
    0.08
     necessários
    0.08
    /sql
    0.07
    ṣiṣẹ
    0.07
    iados
    0.07
     فرصة
    0.07
     준비
    0.07
    訳
    0.07
    Activations Density 0.003%

    No Known Activations