© 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. 96695
    Prev
    Next
    INDEX
    Explanations

    's

    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
     iray
    -0.09
    .wave
    -0.09
     wave
    -0.09
    波
    -0.08
     波
    -0.08
     packets
    -0.08
    	W
    -0.08
     W
    -0.08
    	event
    -0.08
     打
    -0.08
    POSITIVE LOGITS
     lemma
    0.18
     Lem
    0.16
    Lemma
    0.15
    lemma
    0.13
     lem
    0.13
    lemm
    0.10
     Serbia
    0.10
     leon
    0.10
     Andre
    0.10
     Elvis
    0.10
    Activations Density 0.001%

    No Known Activations