© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 49982
    Prev
    Next
    INDEX
    Explanations

    collaps

    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
    نین
    -0.09
     comply
    -0.08
    spot
    -0.08
    slot
    -0.08
    uchtet
    -0.08
    عاية
    -0.07
    kennen
    -0.07
    ствует
    -0.07
    стоящ
    -0.07
     compliance
    -0.07
    POSITIVE LOGITS
    ollapse
    0.16
     collaps
    0.16
     collapse
    0.15
     collapsing
    0.15
    apses
    0.15
    ible
    0.14
     Collapse
    0.14
    Collapse
    0.14
    ibility
    0.14
    -collapse
    0.14
    Activations Density 0.007%

    No Known Activations