© 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. 48535
    Prev
    Next
    INDEX
    Explanations

    code

    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
    €”
    -0.09
    $user
    -0.08
    Mf
    -0.08
    arbeiter
    -0.08
    führer
    -0.08
    _opt
    -0.08
     Wolfgang
    -0.08
     anarch
    -0.08
    igma
    -0.08
    (wx
    -0.08
    POSITIVE LOGITS
     qon
    0.08
     cus
    0.07
     Vid
    0.07
     tante
    0.07
     Jep
    0.07
     dac
    0.07
     tanta
    0.07
     tijekom
    0.07
     citt
    0.07
    vimento
    0.07
    Activations Density 0.000%

    No Known Activations