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. 59340
    Prev
    Next
    INDEX
    Explanations

    descriptive text

    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
     nadr
    -0.08
     normalement
    -0.08
     duly
    -0.08
     knitted
    -0.08
     supporting
    -0.07
    ↵    ↵
    -0.07
     Déf
    -0.07
    lık
    -0.07
    jno
    -0.07
     orientar
    -0.07
    POSITIVE LOGITS
    Advantages
    0.13
    相比
    0.12
     disadvantages
    0.12
     drawbacks
    0.11
     Advantages
    0.11
     cumbersome
    0.10
     Nachteile
    0.10
     advantages
    0.10
     ventajas
    0.10
     vantagens
    0.10
    Activations Density 0.108%

    No Known Activations