© 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. 5907
    Prev
    Next
    INDEX
    Explanations

    �

    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
    нен
    -0.08
    ление
    -0.08
    र्श
    -0.08
    ్మ
    -0.08
     camel
    -0.08
    ರ್ಶ
    -0.07
    نش
    -0.07
     Raleigh
    -0.07
    ृष्ठ
    -0.07
     quest
    -0.07
    POSITIVE LOGITS
    �
    0.15
    �美
    0.13
    occo
    0.09
    �
    0.08
    っと
    0.08
    �
    0.08
    auta
    0.08
    々
    0.08
    bez
    0.08
    Tutor
    0.08
    Activations Density 0.000%

    No Known Activations