Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 112193
    Prev
    Next
    INDEX
    Explanations

    relaxation

    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
     Anzahl
    -0.08
     Friendship
    -0.07
    ноп
    -0.07
     địa
    -0.07
    کله
    -0.07
    größe
    -0.07
     Cube
    -0.07
    ्लिम
    -0.07
     Größe
    -0.07
    اضی
    -0.07
    POSITIVE LOGITS
     muscles
    0.11
     muscle
    0.10
     spieren
    0.09
    肌
    0.08
     Albania
    0.08
     muscular
    0.08
     pistol
    0.08
     músc
    0.08
    hair
    0.08
    ATM
    0.08
    Activations Density 0.008%

    No Known Activations