© 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. 6088
    Prev
    Next
    INDEX
    Explanations

    say "the" or asterisk

    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
    (`[
    -0.08
     phrase
    -0.08
     headset
    -0.08
     termed
    -0.08
    、电
    -0.08
     fryer
    -0.07
     inox
    -0.07
    SUV
    -0.07
    术
    -0.07
    Hindi
    -0.07
    POSITIVE LOGITS
     The
    0.21
    《
    0.20
     《
    0.20
     *
    0.18
    ，《
    0.16
     _
    0.16
     『
    0.14
    	The
    0.14
     *_
    0.14
    "The
    0.14
    Activations Density 0.051%

    No Known Activations