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. 45013
    Prev
    Next
    INDEX
    Explanations

    Lenses and vision correction

    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
     yek
    -0.09
    콩
    -0.09
     hlut
    -0.08
     закон
    -0.08
    уць
    -0.08
     isra
    -0.08
     čin
    -0.08
     antwort
    -0.08
    -nous
    -0.08
     dítě
    -0.08
    POSITIVE LOGITS
    فرة
    0.10
     RO
    0.08
     seamlessly
    0.08
    edas
    0.08
     macros
    0.08
     PO
    0.07
    منة
    0.07
     offerte
    0.07
    ffective
    0.07
     prime
    0.07
    Activations Density 0.003%

    No Known Activations