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. 65105
    Prev
    Next
    INDEX
    Explanations

    You

    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
    pcb
    -0.08
     pathname
    -0.08
    RJ
    -0.07
    .pathname
    -0.07
    ಂಚ
    -0.07
     صالح
    -0.07
    }@
    -0.07
     ವಿದ್ಯ
    -0.07
     narod
    -0.07
     almeno
    -0.07
    POSITIVE LOGITS
    ാക
    0.12
    Paragraph
    0.09
     frases
    0.09
     Paragraph
    0.09
    句
    0.09
    さい
    0.09
     कथ
    0.08
    ാവ
    0.08
     Absatz
    0.08
     seguida
    0.08
    Activations Density 0.072%

    No Known Activations