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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 50852
    Prev
    Next
    INDEX
    Explanations

    say "is" variations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ਸਟ
    -0.12
    स्ट
    -0.12
    സ്റ്റ
    -0.12
    స్ట
    -0.11
    સ્ટ
    -0.11
    ಸ್ಟ
    -0.11
    স্ট
    -0.11
    സ്റ്റ്
    -0.11
     stocks
    -0.10
    ಸ್ಟ್
    -0.10
    POSITIVE LOGITS
    IS
    0.27
    is
    0.25
    િસ
    0.24
    िस
    0.23
    ിസ
    0.23
    	is
    0.22
    িস
    0.22
    ിസ്
    0.22
    isge
    0.22
    Is
    0.21
    Activations Density 0.033%

    No Known Activations