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. 43392
    Prev
    Next
    INDEX
    Explanations

    ons

    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
    美女
    -0.09
     alcalde
    -0.08
    ಬೈ
    -0.08
    APT
    -0.08
     cen
    -0.07
    વામાં
    -0.07
    ıcı
    -0.07
    waiting
    -0.07
    water
    -0.07
    Ingred
    -0.07
    POSITIVE LOGITS
     параметры
    0.08
     tiltak
    0.08
     kreat
    0.08
     paramètres
    0.08
     touchdowns
    0.08
     nombres
    0.07
    🏼
    0.07
     TRACK
    0.07
     chương
    0.07
    esters
    0.07
    Activations Density 0.000%

    No Known Activations