© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 517
    Prev
    Next
    INDEX
    Explanations

    How things work

    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
     जिसे
    -0.10
     who's
    -0.09
     തന്റെ
    -0.09
     ತನ್ನ
    -0.09
     ਜਿਸ
    -0.09
     हूँ
    -0.09
     ਹੈ
    -0.09
     kiu
    -0.08
     الذي
    -0.08
     ఉంద
    -0.08
    POSITIVE LOGITS
     themselves
    0.17
    -elles
    0.13
    -ils
    0.12
     आहेत
    0.12
     নিজেদের
    0.11
    ಿವೆ
    0.11
     которые
    0.11
     joissa
    0.11
     أنفس
    0.11
     जिन्हें
    0.11
    Activations Density 1.312%

    No Known Activations