© 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. 96699
    Prev
    Next
    INDEX
    Explanations

    let

    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
    (final
    -0.11
    	final
    -0.09
    (val
    -0.09
    final
    -0.09
    	val
    -0.09
    val
    -0.09
    cine
    -0.08
     możesz
    -0.08
    readonly
    -0.08
    third
    -0.08
    POSITIVE LOGITS
     let
    0.42
    	let
    0.38
    let
    0.35
    Let
    0.26
     Let
    0.25
    -let
    0.22
    (let
    0.21
     letting
    0.20
    LET
    0.20
     lets
    0.20
    Activations Density 0.006%

    No Known Activations