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. 48644
    Prev
    Next
    INDEX
    Explanations

    b

    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
     citrus
    -0.09
    <h
    -0.08
     بسی
    -0.08
    helu
    -0.08
    onas
    -0.08
    -water
    -0.08
    FLOW
    -0.08
     Stimmung
    -0.08
     sterren
    -0.07
     इतनी
    -0.07
    POSITIVE LOGITS
     formulation
    0.08
     unlink
    0.08
     kombiniert
    0.08
     asymmetric
    0.07
     impair
    0.07
    صيل
    0.07
    0.07
     marrying
    0.07
     opposite
    0.07
    កម្ម
    0.07
    Activations Density 0.025%

    No Known Activations