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. 41958
    Prev
    Next
    INDEX
    Explanations

    tangent

    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
    aae
    -0.09
    ww
    -0.08
    -wow
    -0.08
    קת
    -0.08
     objectively
    -0.08
    -quality
    -0.08
     优
    -0.08
    buy
    -0.08
    /Object
    -0.07
     investidores
    -0.07
    POSITIVE LOGITS
     tan
    0.09
     Generally
    0.08
     tex
    0.08
     poles
    0.07
     محدود
    0.07
    tan
    0.07
     slopes
    0.07
     מוג
    0.07
     horizonte
    0.07
     Seeking
    0.07
    Activations Density 0.015%

    No Known Activations