© 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. 23-RESID-POST-AA
    11. 48180
    Prev
    Next
    INDEX
    Explanations

    punctuation marks

    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
     this
    -0.15
     let's
    -0.15
     what's
    -0.15
     what
    -0.14
    	this
    -0.13
     we'll
    -0.13
     it's
    -0.13
     you'd
    -0.13
     you'll
    -0.13
    	the
    -0.13
    POSITIVE LOGITS
     There
    0.14
     They
    0.14
     It
    0.13
     These
    0.13
     That
    0.12
     This
    0.12
    There
    0.12
     Then
    0.12
     Perhaps
    0.12
     Ես
    0.12
    Activations Density 0.149%

    No Known Activations